AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Decision Trees Recurrently Through Communication

Stephan Alaniz, Diego Marcos, Bernt Schiele, Zeynep Akata

CVPR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Prototype and concept dictionary models · 17 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use recurrent hard binary attribute decisions instead of a classical decision treeRDTC · AWA2mean per-class accuracy: 92.3% vs 98.0%Improved
use recurrent hard binary attribute decisions instead of a classical decision treeRDTC · CUBmean per-class accuracy: 43.5% vs 78.1%Improved
use recurrent hard binary decisions instead of dNDFRDTC · CUBmean per-class accuracy: 73.8% vs 78.1%Improved
add human-annotated attribute lossRDTC · CUBmean per-class accuracy: 78.1 ± 0.2 -> 77.9 ± 0.6Hurt
add human-annotated attribute lossRDTC · AWA2mean per-class accuracy: 98.0 ± 0.1 -> 98.1 ± 0.0Mixed
combine explicit memory with LSTM tree-state encoding (ablation)RDTC · CUBmean per-class accuracy: 73.0 -> 78.1Improved
combine explicit memory with LSTM tree-state encoding (ablation)aRDTC · CUBmean per-class accuracy: 69.1 -> 77.9Improved
encode tree state with explicit memory rather than only the LSTM (ablation)aRDTC · CUBmean per-class accuracy: 69.1% vs. 76.4%Improved
apply classification loss at every communication step rather than only at the leaf (ablation)RDTC · CUB and AWA2intermediate-step accuracyImproved
apply classification loss at every communication step rather than only at the leaf (ablation)RDTC · CUB and AWA2final accuracyNo clear effect
apply classification loss at every communication step rather than only at the leaf (ablation)RDTC · CUB and AWA2number of tree nodesImproved
increase attribute-loss weight λ toward 1.0 (ablation)aRDTC · AWA2 and CUBclassification accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy